© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 73603
    Prev
    Next
    INDEX
    Explanations

    fire and bonfires

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Roller
    -0.85
     Roller
    -0.82
     roller
    -0.72
     зае
    -0.71
    rh
    -0.71
    ocyto
    -0.71
     testing
    -0.69
     tester
    -0.68
     mango
    -0.68
    rimi
    -0.68
    POSITIVE LOGITS
     bonfire
    2.73
     campfire
    2.52
     fires
    2.09
     fire
    1.98
    fires
    1.86
    fire
    1.65
     camp
    1.53
     fireplace
    1.51
     Fires
    1.51
    火
    1.40
    Activations Density 0.016%

    No Known Activations